Model: GELU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 931 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.1550. Min Act: -0.1700

Data Index: 742537 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.0604. Min Act: -0.1700

Data Index: 1352994 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.0762. Min Act: -0.1700

Data Index: 412016 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.0604. Min Act: -0.1700

Data Index: 1345563 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.0446. Min Act: -0.1700

Data Index: 192738 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.0288. Min Act: -0.1700

Data Index: 715147 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.0130. Min Act: -0.1700

Data Index: 1078019 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.0130. Min Act: -0.1700

Data Index: 600913 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.0130. Min Act: -0.1700

Data Index: 167346 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.0288. Min Act: -0.1700

Data Index: 44607 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.0130. Min Act: -0.1700

Data Index: 1249594 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.0130. Min Act: -0.1700

Data Index: 559687 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.0288. Min Act: -0.1700

Data Index: 685274 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.0446. Min Act: -0.1700

Data Index: 320890 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 3.1550. Min Range: -3.1550

Max Act: 2.9972. Min Act: -0.1700

Data Index: 471499 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.0130. Min Act: -0.1700

Data Index: 562800 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.0130. Min Act: -0.1700

Data Index: 192544 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 3.1550. Min Range: -3.1550

Max Act: 2.9814. Min Act: -0.1700

Data Index: 336591 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 3.1550. Min Range: -3.1550

Max Act: 3.0130. Min Act: -0.1700

Data Index: 88787 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 3.1550. Min Range: -3.1550

Max Act: 2.9972. Min Act: -0.1700

Data Index: 869638 (C4 (Web Text))

Max Activating Token Index: 500